© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90508
    Prev
    Next
    INDEX
    Explanations

    inheritance and medical conditions

    np_acts-logits-general · gemini-2.5-flash-lite

    choosing between options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     孔
    0.53
     prilikom
    0.52
     utilisent
    0.49
     असतो
    0.48
    Controllers
    0.47
    の
    0.46
     použí
    0.46
    ၿ
    0.46
     ระบบ
    0.45
    임
    0.44
    POSITIVE LOGITS
     neoplas
    0.47
    ަރ
    0.47
     Inheritance
    0.45
     cáncer
    0.44
    <0xBC>
    0.44
     inherited
    0.44
    <0xB3>
    0.44
     Honestly
    0.44
     अस्पताल
    0.44
     सर्जरी
    0.44
    Activations Density 0.001%

    No Known Activations